Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add stdout option (#3027) 

* add add cli options for play and speed
--play argument uses simpleaudio to play the tts wav
--speed <float 0.0-2.0> passes speed argument to Coqui Studio models

* remove simpleaudio not referenced in file

* fix simpleaudio dependency version

* add ALSA headers for simpleaudio compilation

* Dockerfile ALSA headers for simpleaudio

* base changes to use stdout instead of play audio
Considering conversion to pipe wav data for audio playback with ohter program
like aplay.

This is incomplete code. Using to get feedback before proceeding with
implementation.

* remove play for pipe_out arg that suppresses stdout
removed play and simpleaudio dependency in place of pipe
fuctionality to allow passing wav file data to a program
dedicated to playing audio.

* scipy.io.wavfile.write fails with /dev/null target

* Streaming inference for XTTS 🚀 (#3035)

* v0.17.7

* Redownload XTTS with the local and remote config do not match

* Remove unused method

* Print a message when it is already donwloaded

* Try-except to present error when the user dont have connection

* Fix style

* 0.17.8

* v0.17.8

---------

Co-authored-by: Julian Weber <julian.weber@hotmail.fr>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
Co-authored-by: Edresson Casanova <edresson1@gmail.com>
Co-authored-by: ggoknar <ggoknar@coqui.ai>
This commit is contained in:
David Garvey 2023-10-16 05:07:21 -05:00 committed by GitHub
parent cae185fd16
commit a151d70242
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
8 changed files with 246 additions and 150 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -347,6 +347,18 @@ If you don't specify any models, then it uses LJSpeech based English model.
$ tts --text "Text for TTS" --out_path output/path/speech.wav
```
- Run TTS and pipe out the generated TTS wav file data:
```
$ tts --text "Text for TTS" --pipe_out --out_path output/path/speech.wav | aplay
```
- Run TTS and define speed factor to use for 🐸Coqui Studio models, between 0.0 and 2.0:
```
$ tts --text "Text for TTS" --model_name "coqui_studio/<language>/<dataset>/<model_name>" --speed 1.2 --out_path output/path/speech.wav
```
- Run a TTS model with its default vocoder model:
```

18
TTS/api.py
View File

@ -112,7 +112,6 @@ class TTS(nn.Module):
return self.synthesizer.tts_model.language_manager.num_languages > 1
return False
@property
def speakers(self):
if not self.is_multi_speaker:
@ -265,6 +264,7 @@ class TTS(nn.Module):
language: str = None,
emotion: str = None,
speed: float = 1.0,
pipe_out = None,
file_path: str = None,
) -> Union[np.ndarray, str]:
"""Convert text to speech using Coqui Studio models. Use `CS_API` class if you are only interested in the API.
@ -281,6 +281,8 @@ class TTS(nn.Module):
with "V1" model. Defaults to None.
speed (float, optional):
Speed of the speech. Defaults to 1.0.
pipe_out (BytesIO, optional):
Flag to stdout the generated TTS wav file for shell pipe.
file_path (str, optional):
Path to save the output file. When None it returns the `np.ndarray` of waveform. Defaults to None.
@ -294,6 +296,7 @@ class TTS(nn.Module):
speaker_name=speaker_name,
language=language,
speed=speed,
pipe_out=pipe_out,
emotion=emotion,
file_path=file_path,
)[0]
@ -356,6 +359,7 @@ class TTS(nn.Module):
speaker_wav: str = None,
emotion: str = None,
speed: float = 1.0,
pipe_out = None,
file_path: str = "output.wav",
**kwargs,
):
@ -377,6 +381,8 @@ class TTS(nn.Module):
Emotion to use for 🐸Coqui Studio models. Defaults to "Neutral".
speed (float, optional):
Speed factor to use for 🐸Coqui Studio models, between 0.0 and 2.0. Defaults to None.
pipe_out (BytesIO, optional):
Flag to stdout the generated TTS wav file for shell pipe.
file_path (str, optional):
Output file path. Defaults to "output.wav".
kwargs (dict, optional):
@ -386,10 +392,16 @@ class TTS(nn.Module):
if self.csapi is not None:
return self.tts_coqui_studio(
text=text, speaker_name=speaker, language=language, emotion=emotion, speed=speed, file_path=file_path
text=text,
speaker_name=speaker,
language=language,
emotion=emotion,
speed=speed,
file_path=file_path,
pipe_out=pipe_out,
)
wav = self.tts(text=text, speaker=speaker, language=language, speaker_wav=speaker_wav, **kwargs)
self.synthesizer.save_wav(wav=wav, path=file_path)
self.synthesizer.save_wav(wav=wav, path=file_path, pipe_out=pipe_out)
return file_path
def voice_conversion(

317
TTS/bin/synthesize.py
View File

@ -2,6 +2,7 @@
# -*- coding: utf-8 -*-
import argparse
import contextlib
import sys
from argparse import RawTextHelpFormatter
@ -59,6 +60,18 @@ If you don't specify any models, then it uses LJSpeech based English model.
$ tts --text "Text for TTS" --out_path output/path/speech.wav
```
- Run TTS and pipe out the generated TTS wav file data:
```
$ tts --text "Text for TTS" --pipe_out --out_path output/path/speech.wav | aplay
```
- Run TTS and define speed factor to use for 🐸Coqui Studio models, between 0.0 and 2.0:
```
$ tts --text "Text for TTS" --model_name "coqui_studio/<language>/<dataset>/<model_name>" --speed 1.2 --out_path output/path/speech.wav
```
- Run a TTS model with its default vocoder model:
```
@ -228,6 +241,20 @@ def main():
help="Language to condition the model with. Only available for 🐸Coqui Studio `XTTS-multilingual` model.",
default=None,
)
parser.add_argument(
"--pipe_out",
help="stdout the generated TTS wav file for shell pipe.",
type=str2bool,
nargs="?",
const=True,
default=False,
)
parser.add_argument(
"--speed",
type=float,
help="Speed factor to use for 🐸Coqui Studio models, between 0.0 and 2.0.",
default=None,
)
# args for multi-speaker synthesis
parser.add_argument("--speakers_file_path", type=str, help="JSON file for multi-speaker model.", default=None)
@ -335,167 +362,177 @@ def main():
if not any(check_args):
parser.parse_args(["-h"])
# Late-import to make things load faster
from TTS.api import TTS
from TTS.utils.manage import ModelManager
from TTS.utils.synthesizer import Synthesizer
pipe_out = sys.stdout if args.pipe_out else None
# load model manager
path = Path(__file__).parent / "../.models.json"
manager = ModelManager(path, progress_bar=args.progress_bar)
api = TTS()
with contextlib.redirect_stdout(None if args.pipe_out else sys.stdout):
# Late-import to make things load faster
from TTS.api import TTS
from TTS.utils.manage import ModelManager
from TTS.utils.synthesizer import Synthesizer
tts_path = None
tts_config_path = None
speakers_file_path = None
language_ids_file_path = None
vocoder_path = None
vocoder_config_path = None
encoder_path = None
encoder_config_path = None
vc_path = None
vc_config_path = None
model_dir = None
# load model manager
path = Path(__file__).parent / "../.models.json"
manager = ModelManager(path, progress_bar=args.progress_bar)
api = TTS()
# CASE1 #list : list pre-trained TTS models
if args.list_models:
manager.add_cs_api_models(api.list_models())
manager.list_models()
sys.exit()
tts_path = None
tts_config_path = None
speakers_file_path = None
language_ids_file_path = None
vocoder_path = None
vocoder_config_path = None
encoder_path = None
encoder_config_path = None
vc_path = None
vc_config_path = None
model_dir = None
# CASE2 #info : model info for pre-trained TTS models
if args.model_info_by_idx:
model_query = args.model_info_by_idx
manager.model_info_by_idx(model_query)
sys.exit()
# CASE1 #list : list pre-trained TTS models
if args.list_models:
manager.add_cs_api_models(api.list_models())
manager.list_models()
sys.exit()
if args.model_info_by_name:
model_query_full_name = args.model_info_by_name
manager.model_info_by_full_name(model_query_full_name)
sys.exit()
# CASE2 #info : model info for pre-trained TTS models
if args.model_info_by_idx:
model_query = args.model_info_by_idx
manager.model_info_by_idx(model_query)
sys.exit()
# CASE3: TTS with coqui studio models
if "coqui_studio" in args.model_name:
print(" > Using 🐸Coqui Studio model: ", args.model_name)
api = TTS(model_name=args.model_name, cs_api_model=args.cs_model)
api.tts_to_file(text=args.text, emotion=args.emotion, file_path=args.out_path, language=args.language)
print(" > Saving output to ", args.out_path)
return
if args.model_info_by_name:
model_query_full_name = args.model_info_by_name
manager.model_info_by_full_name(model_query_full_name)
sys.exit()
# CASE4: load pre-trained model paths
if args.model_name is not None and not args.model_path:
model_path, config_path, model_item = manager.download_model(args.model_name)
# tts model
if model_item["model_type"] == "tts_models":
tts_path = model_path
tts_config_path = config_path
if "default_vocoder" in model_item:
args.vocoder_name = model_item["default_vocoder"] if args.vocoder_name is None else args.vocoder_name
# CASE3: TTS with coqui studio models
if "coqui_studio" in args.model_name:
print(" > Using 🐸Coqui Studio model: ", args.model_name)
api = TTS(model_name=args.model_name, cs_api_model=args.cs_model)
api.tts_to_file(
text=args.text,
emotion=args.emotion,
file_path=args.out_path,
language=args.language,
speed=args.speed,
pipe_out=pipe_out,
)
print(" > Saving output to ", args.out_path)
return
# voice conversion model
if model_item["model_type"] == "voice_conversion_models":
vc_path = model_path
vc_config_path = config_path
# CASE4: load pre-trained model paths
if args.model_name is not None and not args.model_path:
model_path, config_path, model_item = manager.download_model(args.model_name)
# tts model
if model_item["model_type"] == "tts_models":
tts_path = model_path
tts_config_path = config_path
if "default_vocoder" in model_item:
args.vocoder_name = model_item["default_vocoder"] if args.vocoder_name is None else args.vocoder_name
# tts model with multiple files to be loaded from the directory path
if model_item.get("author", None) == "fairseq" or isinstance(model_item["model_url"], list):
model_dir = model_path
tts_path = None
tts_config_path = None
args.vocoder_name = None
# voice conversion model
if model_item["model_type"] == "voice_conversion_models":
vc_path = model_path
vc_config_path = config_path
# load vocoder
if args.vocoder_name is not None and not args.vocoder_path:
vocoder_path, vocoder_config_path, _ = manager.download_model(args.vocoder_name)
# tts model with multiple files to be loaded from the directory path
if model_item.get("author", None) == "fairseq" or isinstance(model_item["model_url"], list):
model_dir = model_path
tts_path = None
tts_config_path = None
args.vocoder_name = None
# CASE5: set custom model paths
if args.model_path is not None:
tts_path = args.model_path
tts_config_path = args.config_path
speakers_file_path = args.speakers_file_path
language_ids_file_path = args.language_ids_file_path
# load vocoder
if args.vocoder_name is not None and not args.vocoder_path:
vocoder_path, vocoder_config_path, _ = manager.download_model(args.vocoder_name)
if args.vocoder_path is not None:
vocoder_path = args.vocoder_path
vocoder_config_path = args.vocoder_config_path
# CASE5: set custom model paths
if args.model_path is not None:
tts_path = args.model_path
tts_config_path = args.config_path
speakers_file_path = args.speakers_file_path
language_ids_file_path = args.language_ids_file_path
if args.encoder_path is not None:
encoder_path = args.encoder_path
encoder_config_path = args.encoder_config_path
if args.vocoder_path is not None:
vocoder_path = args.vocoder_path
vocoder_config_path = args.vocoder_config_path
device = args.device
if args.use_cuda:
device = "cuda"
if args.encoder_path is not None:
encoder_path = args.encoder_path
encoder_config_path = args.encoder_config_path
# load models
synthesizer = Synthesizer(
tts_path,
tts_config_path,
speakers_file_path,
language_ids_file_path,
vocoder_path,
vocoder_config_path,
encoder_path,
encoder_config_path,
vc_path,
vc_config_path,
model_dir,
args.voice_dir,
).to(device)
device = args.device
if args.use_cuda:
device = "cuda"
# query speaker ids of a multi-speaker model.
if args.list_speaker_idxs:
print(
" > Available speaker ids: (Set --speaker_idx flag to one of these values to use the multi-speaker model."
)
print(synthesizer.tts_model.speaker_manager.name_to_id)
return
# load models
synthesizer = Synthesizer(
tts_path,
tts_config_path,
speakers_file_path,
language_ids_file_path,
vocoder_path,
vocoder_config_path,
encoder_path,
encoder_config_path,
vc_path,
vc_config_path,
model_dir,
args.voice_dir,
).to(device)
# query langauge ids of a multi-lingual model.
if args.list_language_idxs:
print(
" > Available language ids: (Set --language_idx flag to one of these values to use the multi-lingual model."
)
print(synthesizer.tts_model.language_manager.name_to_id)
return
# query speaker ids of a multi-speaker model.
if args.list_speaker_idxs:
print(
" > Available speaker ids: (Set --speaker_idx flag to one of these values to use the multi-speaker model."
)
print(synthesizer.tts_model.speaker_manager.name_to_id)
return
# check the arguments against a multi-speaker model.
if synthesizer.tts_speakers_file and (not args.speaker_idx and not args.speaker_wav):
print(
" [!] Looks like you use a multi-speaker model. Define `--speaker_idx` to "
"select the target speaker. You can list the available speakers for this model by `--list_speaker_idxs`."
)
return
# query langauge ids of a multi-lingual model.
if args.list_language_idxs:
print(
" > Available language ids: (Set --language_idx flag to one of these values to use the multi-lingual model."
)
print(synthesizer.tts_model.language_manager.name_to_id)
return
# RUN THE SYNTHESIS
if args.text:
print(" > Text: {}".format(args.text))
# check the arguments against a multi-speaker model.
if synthesizer.tts_speakers_file and (not args.speaker_idx and not args.speaker_wav):
print(
" [!] Looks like you use a multi-speaker model. Define `--speaker_idx` to "
"select the target speaker. You can list the available speakers for this model by `--list_speaker_idxs`."
)
return
# kick it
if tts_path is not None:
wav = synthesizer.tts(
args.text,
speaker_name=args.speaker_idx,
language_name=args.language_idx,
speaker_wav=args.speaker_wav,
reference_wav=args.reference_wav,
style_wav=args.capacitron_style_wav,
style_text=args.capacitron_style_text,
reference_speaker_name=args.reference_speaker_idx,
)
elif vc_path is not None:
wav = synthesizer.voice_conversion(
source_wav=args.source_wav,
target_wav=args.target_wav,
)
elif model_dir is not None:
wav = synthesizer.tts(
args.text, speaker_name=args.speaker_idx, language_name=args.language_idx, speaker_wav=args.speaker_wav
)
# RUN THE SYNTHESIS
if args.text:
print(" > Text: {}".format(args.text))
# save the results
print(" > Saving output to {}".format(args.out_path))
synthesizer.save_wav(wav, args.out_path)
# kick it
if tts_path is not None:
wav = synthesizer.tts(
args.text,
speaker_name=args.speaker_idx,
language_name=args.language_idx,
speaker_wav=args.speaker_wav,
reference_wav=args.reference_wav,
style_wav=args.capacitron_style_wav,
style_text=args.capacitron_style_text,
reference_speaker_name=args.reference_speaker_idx,
)
elif vc_path is not None:
wav = synthesizer.voice_conversion(
source_wav=args.source_wav,
target_wav=args.target_wav,
)
elif model_dir is not None:
wav = synthesizer.tts(
args.text, speaker_name=args.speaker_idx, language_name=args.language_idx, speaker_wav=args.speaker_wav
)
# save the results
print(" > Saving output to {}".format(args.out_path))
synthesizer.save_wav(wav, args.out_path, pipe_out=pipe_out)
if __name__ == "__main__":

6
TTS/cs_api.py
View File

@ -9,6 +9,8 @@ import numpy as np
import requests
from scipy.io import wavfile
from TTS.utils.audio.numpy_transforms import save_wav
class Speaker(object):
"""Convert dict to object."""
@ -288,6 +290,7 @@ class CS_API:
speaker_id=None,
emotion=None,
speed=1.0,
pipe_out=None,
language=None,
file_path: str = None,
) -> str:
@ -300,6 +303,7 @@ class CS_API:
speaker_id (str): Speaker ID. If None, the speaker name is used.
emotion (str): Emotion of the speaker. One of "Neutral", "Happy", "Sad", "Angry", "Dull".
speed (float): Speed of the speech. 1.0 is normal speed.
pipe_out (BytesIO, optional): Flag to stdout the generated TTS wav file for shell pipe.
language (str): Language of the text. If None, the default language of the speaker is used. Language is only
supported by `XTTS-multilang` model. Currently supports en, de, es, fr, it, pt, pl. Defaults to "en".
file_path (str): Path to save the file. If None, a temporary file is created.
@ -307,7 +311,7 @@ class CS_API:
if file_path is None:
file_path = tempfile.mktemp(".wav")
wav, sr = self.tts(text, speaker_name, speaker_id, emotion, speed, language)
wavfile.write(file_path, sr, wav)
save_wav(wav=wav, path=file_path, sample_rate=sr, pipe_out=pipe_out)
return file_path

13
TTS/utils/audio/numpy_transforms.py
View File

@ -1,3 +1,4 @@
from io import BytesIO
from typing import Tuple
import librosa
@ -427,16 +428,24 @@ def load_wav(*, filename: str, sample_rate: int = None, resample: bool = False,
return x
def save_wav(*, wav: np.ndarray, path: str, sample_rate: int = None, **kwargs) -> None:
def save_wav(*, wav: np.ndarray, path: str, sample_rate: int = None, pipe_out = None, **kwargs) -> None:
"""Save float waveform to a file using Scipy.
Args:
wav (np.ndarray): Waveform with float values in range [-1, 1] to save.
path (str): Path to a output file.
sr (int, optional): Sampling rate used for saving to the file. Defaults to None.
pipe_out (BytesIO, optional): Flag to stdout the generated TTS wav file for shell pipe.
"""
wav_norm = wav * (32767 / max(0.01, np.max(np.abs(wav))))
scipy.io.wavfile.write(path, sample_rate, wav_norm.astype(np.int16))
wav_norm = wav_norm.astype(np.int16)
if pipe_out:
wav_buffer = BytesIO()
scipy.io.wavfile.write(wav_buffer, sample_rate, wav_norm)
wav_buffer.seek(0)
pipe_out.buffer.write(wav_buffer.read())
scipy.io.wavfile.write(path, sample_rate, wav_norm)
def mulaw_encode(*, wav: np.ndarray, mulaw_qc: int, **kwargs) -> np.ndarray:

12
TTS/utils/audio/processor.py
View File

@ -1,3 +1,4 @@
from io import BytesIO
from typing import Dict, Tuple
import librosa
@ -693,20 +694,27 @@ class AudioProcessor(object):
x = self.rms_volume_norm(x, self.db_level)
return x
def save_wav(self, wav: np.ndarray, path: str, sr: int = None) -> None:
def save_wav(self, wav: np.ndarray, path: str, sr: int = None, pipe_out = None) -> None:
"""Save a waveform to a file using Scipy.
Args:
wav (np.ndarray): Waveform to save.
path (str): Path to a output file.
sr (int, optional): Sampling rate used for saving to the file. Defaults to None.
pipe_out (BytesIO, optional): Flag to stdout the generated TTS wav file for shell pipe.
"""
if self.do_rms_norm:
wav_norm = self.rms_volume_norm(wav, self.db_level) * 32767
else:
wav_norm = wav * (32767 / max(0.01, np.max(np.abs(wav))))
scipy.io.wavfile.write(path, sr if sr else self.sample_rate, wav_norm.astype(np.int16))
wav_norm = wav_norm.astype(np.int16)
if pipe_out:
wav_buffer = BytesIO()
scipy.io.wavfile.write(wav_buffer, sr if sr else self.sample_rate, wav_norm)
wav_buffer.seek(0)
pipe_out.buffer.write(wav_buffer.read())
scipy.io.wavfile.write(path, sr if sr else self.sample_rate, wav_norm)
def get_duration(self, filename: str) -> float:
"""Get the duration of a wav file using Librosa.

5
TTS/utils/synthesizer.py
View File

@ -235,19 +235,20 @@ class Synthesizer(nn.Module):
"""
return self.seg.segment(text)
def save_wav(self, wav: List[int], path: str) -> None:
def save_wav(self, wav: List[int], path: str, pipe_out = None) -> None:
"""Save the waveform as a file.
Args:
wav (List[int]): waveform as a list of values.
path (str): output path to save the waveform.
pipe_out (BytesIO, optional): Flag to stdout the generated TTS wav file for shell pipe.
"""
# if tensor convert to numpy
if torch.is_tensor(wav):
wav = wav.cpu().numpy()
if isinstance(wav, list):
wav = np.array(wav)
save_wav(wav=wav, path=path, sample_rate=self.output_sample_rate)
save_wav(wav=wav, path=path, sample_rate=self.output_sample_rate, pipe_out=pipe_out)
def voice_conversion(self, source_wav: str, target_wav: str) -> List[int]:
output_wav = self.vc_model.voice_conversion(source_wav, target_wav)

13
tests/api_tests/test_synthesize_api.py
View File

@ -13,3 +13,16 @@ def test_synthesize():
'--text "This is it" '
f'--out_path "{output_path}"'
)
# 🐸 Coqui studio model with speed arg.
run_cli(
'tts --model_name "coqui_studio/en/Torcull Diarmuid/coqui_studio" '
'--text "This is it but slow" --speed 0.1'
f'--out_path "{output_path}"'
)
# test pipe_out command
run_cli(
'tts --text "test." --pipe_out '
f'--out_path "{output_path}" | aplay'
)